Study on automatic detection and classification of breast nodule using deep convolutional neural network system

被引:29
作者
Wang, Feiqian [1 ]
Liu, Xiaotong [2 ,3 ]
Yuan, Na [1 ]
Qian, Buyue [2 ,3 ]
Ruan, Litao [1 ]
Yin, Changchang [2 ,3 ]
Jin, Ciping [2 ,3 ]
机构
[1] Xi An Jiao Tong Univ, Dept Ultrasound, Affiliated Hosp 1, Xian, Peoples R China
[2] Xi An Jiao Tong Univ, Natl Engn Lab Big Data Analyt, 28 Xianning West Rd, Xian 710049, Peoples R China
[3] Xi An Jiao Tong Univ, Sch Elect & Informat Engn, Xian, Peoples R China
关键词
Deep convolutional neural networks (CNN); automated breast ultrasound (ABUS); breast nodule; computer-aided diagnosis (CAD); TUMOR-DETECTION; ULTRASOUND; CANCER; SEGMENTATION; DISCRIMINATION; LESIONS; BENIGN;
D O I
10.21037/jtd-19-3013
中图分类号
R56 [呼吸系及胸部疾病];
学科分类号
摘要
Backgrounds: Conventional ultrasound manual scanning and artificial diagnosis approaches in breast are considered to be operator-dependence, slight slow and error-prone. In this study, we used Automated Breast Ultrasound (ABUS) machine for the scanning, and deep convolutional neural network (CNN) technology, a kind of Deep Learning (DL) algorithm, for the detection and classification of breast nodules, aiming to achieve the automatic and accurate diagnosis of breast nodules. Methods: Two hundred and ninety-three lesions from 194 patients with definite pathological diagnosis results (117 benign and 176 malignancy) were recruited as case group. Another 70 patients without breast diseases were enrolled as control group. All the breast scans were carried out by an ABUS machine and then randomly divided into training set, verification set and test set, with a proportion of 7:1:2. In the training set, we constructed a detection model by a three-dimensionally U-shaped convolutional neural network (3D U-Net) architecture for the purpose of segment the nodules from background breast images. Processes such as residual block, attention connections, and hard mining were used to optimize the model while strategies of random cropping, flipping and rotation for data augmentation. In the test phase, the current model was compared with those in previously reported studies. In the verification set, the detection effectiveness of detection model was evaluated. In the classification phase, multiple convolutional layers and fully-connected layers were applied to set up a classification model, aiming to identify whether the nodule was malignancy. Results: Our detection model yielded a sensitivity of 91% and 1.92 false positive subjects per automatically scanned imaging. The classification model achieved a sensitivity of 87.0%, a specificity of 88.0% and an accuracy of 87.5%. Conclusions: Deep CNN combined with ABUS maybe a promising tool for easy detection and accurate diagnosis of breast nodule.
引用
收藏
页码:4690 / 4701
页数:12
相关论文
共 46 条
[1]  
[Anonymous], 2016, MED IMAGE COMPUTING
[2]  
[Anonymous], 2018, AMIA ANN S P
[3]   Recall rate of screening ultrasound with automated breast volumetric scanning (ABVS) in women with dense breasts: a first quarter experience [J].
Arleo, Elizabeth Kagan ;
Saleh, Marwa ;
Ionescu, Dana ;
Drotman, Michele ;
Min, Robert J. ;
Hentel, Keith .
CLINICAL IMAGING, 2014, 38 (04) :439-444
[4]   Tumor Detection in Automated Breast Ultrasound Using 3-D CNN and Prioritized Candidate Aggregation [J].
Chiang, Tsung-Chen ;
Huang, Yao-Sian ;
Chen, Rong-Tai ;
Huang, Chiun-Sheng ;
Chang, Ruey-Feng .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2019, 38 (01) :240-249
[5]   Breast Cancer Screening, Mammography, and Other Modalities [J].
Fiorica, James V. .
CLINICAL OBSTETRICS AND GYNECOLOGY, 2016, 59 (04) :688-709
[6]   Analysis of False-Negative Readings of Automated Breast Ultrasound Studies [J].
Grubstein, Ahuva ;
Rapson, Yael ;
Gadiel, Itai ;
Cohen, Maya .
JOURNAL OF CLINICAL ULTRASOUND, 2017, 45 (05) :245-251
[7]   Evaluating the effect of Avastin on breast cancer angiogenesis using synchrotron radiation [J].
Gu, Shengmei ;
Xue, Jingyan ;
Xi, Yan ;
Tang, Rongbiao ;
Jin, Wei ;
Chen, Jia-Jian ;
Zhang, Xi ;
Shao, Zhi-Min ;
Wu, Jiong .
QUANTITATIVE IMAGING IN MEDICINE AND SURGERY, 2019, 9 (03) :418-426
[8]   Radiomics Analysis on Ultrasound for Prediction of Biologic Behavior in Breast Invasive Ductal Carcinoma [J].
Guo, Yi ;
Hu, Yuzhou ;
Qiao, Mengyun ;
Wang, Yuanyuan ;
Yu, Jinhua ;
Li, Jiawei ;
Chang, Cai .
CLINICAL BREAST CANCER, 2018, 18 (03) :E335-E344
[9]   Computer-Aided Diagnosis Scheme for Distinguishing Between Benign and Malignant Masses in Breast DCE-MRI [J].
Honda, Emi ;
Nakayama, Ryohei ;
Koyama, Hitoshi ;
Yamashita, Akiyoshi .
JOURNAL OF DIGITAL IMAGING, 2016, 29 (03) :388-393
[10]   Machine Learning in Ultrasound Computer-Aided Diagnostic Systems: A Survey [J].
Huang, Qinghua ;
Zhang, Fan ;
Li, Xuelong .
BIOMED RESEARCH INTERNATIONAL, 2018, 2018